A deep transfer learning approach for wearable sleep stage classification with photoplethysmography

Abstract

Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better sleep disorder screening and health monitoring. However, PPG is rarely included in large sleep studies with gold-standard sleep annotation from polysomnography. Therefore, training data-intensive state-of-the-art deep neural networks is challenging. In this work a deep recurrent neural network is first trained using a large sleep data set with electrocardiogram (ECG) data (292 participants, 584 recordings) to perform 4-class sleep stage classification (wake, rapid-eye-movement, N1/N2, and N3). A small part of its weights is adapted to a smaller, newer PPG data set (60 healthy participants, 101 recordings) through three variations of transfer learning. Best results (Cohen’s kappa of 0.65 ± 0.11, accuracy of 76.36 ± 7.57%) were achieved with the domain and decision combined transfer learning strategy, significantly outperforming the PPG-trained and ECG-trained baselines. This performance for PPG-based 4-class sleep stage classification is unprecedented in literature, bringing home sleep stage monitoring closer to clinical use. The work demonstrates the merit of transfer learning in developing reliable methods for new sensor technologies by reusing similar, older non-wearable data sets. Further study should evaluate our approach in patients with sleep disorders such as insomnia and sleep apnoea.

SleepPPG-Net: a deep learning algorithm for robust sleep staging from continuous photoplethysmography

“…On the held out test set of 204 MESA patients, SleepPPG-Net scored a κ of 0.75 against 0.66 for BM-FE and 0.69 for BM-DTS approaches. SleepPPG-Net performance is also significantly (p < 0.001, two-sample t-test) higher than the current published SOTA results for sleep staging from PPG which stand at a κ of 0.66 [22,23], and significantly (p = 0.02, two-sample t-test) higher than the current SOTA results for sleepsleep staging from ECG which are reported at κ of 0.69 [20]. Figure 9 presents an example of the hypnograms generated by BM-FE, DB-DTS and SleepPPG-Net for a single patient.…”

“…Most works that use PPG usually do so in the context of transfer learning (TL), where models are trained on a large database of heart rate variability (HRV) measures and then fine-tuned to a smaller database of pulse rate variability (PRV) measures derived from the IBIs detected on the PPG. These works report κ performance approaching 0.66 [22,23]. Sleep staging from the raw PPG is a relatively novel approach.…”

Multi-label classification for multi-drug resistance prediction of Escherichia coli

“…For instance, Yang et al , [12] and Kouchaki et al ., [13] used different machine learning algorithms, namely support vector machine (SVM), logistic regression (LR), and random forest (RF) to predict AMR from whole-genome sequencing data and achieved high accuracy prediction. Other approaches also included deep learning to predict new antibiotic drugs, AMR genes, and AMR peptides [14] , [15] , [16] , [17] , [18] , [19] , [20] . However, all of these studies are based on single drug resistance information and do not take into account the MDR information of the bacteria.…”

Hybrid Sleep Stage Classification for Clinical Practices across Different Polysomnography Systems Using Frontal EEG

“…The percentage and destitution of each sleep stage class are then used to evaluate sleep quality. While the simple identification between wake, REM sleep, and NREM sleep can be achieved using ECG [6], photoplethysmography [7], oximetry [8] or body movement [9], EEG or EOG signals are still required to correctly distinguish the different sleep stages. The need for multiple channels has kept the measurement of sleep quality from mass deployment outside of dedicated sleep laboratories.…”